Instructions to use navthings/lilbase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use navthings/lilbase with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf navthings/lilbase:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf navthings/lilbase:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf navthings/lilbase:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf navthings/lilbase:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf navthings/lilbase:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf navthings/lilbase:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf navthings/lilbase:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf navthings/lilbase:Q4_K_M

Use Docker

docker model run hf.co/navthings/lilbase:Q4_K_M

LM Studio
Jan

vLLM

How to use navthings/lilbase with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "navthings/lilbase"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "navthings/lilbase",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/navthings/lilbase:Q4_K_M

Ollama
How to use navthings/lilbase with Ollama:
```
ollama run hf.co/navthings/lilbase:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use navthings/lilbase with Docker Model Runner:
```
docker model run hf.co/navthings/lilbase:Q4_K_M
```

Lemonade

How to use navthings/lilbase with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull navthings/lilbase:Q4_K_M

Run and chat with the model

lemonade run user.lilbase-Q4_K_M

List all available models

lemonade list

Atomic Chat
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

lilbase

a 297m param llama-style base model trained from scratch on a kaggle tpu v5e-8.

its a base model, so it continues text instead of answering questions. give it the start of a sentence, not a question. grammar is solid, facts are confidently made up. for the chat version see lilchat.

run it

ollama run navthings/lilbase "The water cycle begins when"

or try it in your browser: https://navthings.github.io/playground/

files

file	size	notes
`model.safetensors` + config + tokenizer	1.19gb	transformers `LlamaForCausalLM`
`lilbase-q8_0.gguf`	379mb	same perplexity as f16
`lilbase-q4_k_m.gguf`	274mb	~0.8% higher perplexity, smallest

the model

gqa, rope, rmsnorm, swiglu. 24 layers, d=1024, 16 query heads, 4 kv heads, 1024 context. llama tokenizer, 32k vocab. tied embeddings.

trained on 6.1b tokens of fineweb-edu (sample-10BT), roughly chinchilla-optimal for this size. 11,043 steps of 524k tokens, data parallel over 8 tpu chips. held-out loss 2.608.

vs gpt-2 small

benchmark	lilbase	gpt-2 124m
hellaswag (acc_norm)	41.0%	31.1%
arc-easy (acc_norm)	50.5%	39.5%
lambada	28.7%	32.6%

code

https://github.com/navthings/lilbase

Downloads last month: 264

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for navthings/lilbase

Quantizations

1 model

navthings
/

lilbase